© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19557
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transférez
    -0.88
    GEBURTSDATUM
    -0.88
    énario
    -0.85
    脚注の使い方
    -0.81
    ⓧ
    -0.78
    Cyfeiriadau
    -0.72
    PostInfinity
    -0.70
    MENAFN
    -0.69
    клопе
    -0.68
    verwijspagina
    -0.68
    POSITIVE LOGITS
    gulp
    0.54
     panoramique
    0.51
     financières
    0.49
     descansar
    0.49
     présidenti
    0.48
     trúc
    0.45
     refroid
    0.45
     franquicia
    0.45
     kohta
    0.45
    ColumnHeader
    0.45
    Activations Density 0.013%

    No Known Activations